# Towards Stable and Comprehensive Domain Alignment: Max-Margin Domain-Adversarial Training

arXiv: https://arxiv.org/abs/2003.13249 · HTML: https://mlsanity.com/paper/2003.13249/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Mar 2020.

## Built on by (most cited first, 3 of 3)

- [SenseFi: A Library and Benchmark on Deep-Learning-Empowered WiFi Human Sensing](https://mlsanity.com/paper/2207.07859/) (2022)
- [centroIDA: Cross-Domain Class Discrepancy Minimization Based on Accumulative Class-Centroids for Imbalanced Domain Adaptation](https://mlsanity.com/paper/2308.10619/) (2023)
- [A swap-adversarial framework for improving domain generalization in electrocorticography-based Parkinson's disease classification](https://mlsanity.com/paper/2602.10528/) (2026)

## Abstract (arXiv)

Domain adaptation tackles the problem of transferring knowledge from a label-rich source domain to a label-scarce or even unlabeled target domain. Recently domain-adversarial training (DAT) has shown promising capacity to learn a domain-invariant feature space by reversing the gradient propagation of a domain classifier. However, DAT is still vulnerable in several aspects including (1) training instability due to the overwhelming discriminative ability of the domain classifier in adversarial training, (2) restrictive feature-level alignment, and (3) lack of interpretability or systematic explanation of the learned feature space. In this paper, we propose a novel Max-margin Domain-Adversarial Training (MDAT) by designing an Adversarial Reconstruction Network (ARN). The proposed MDAT stabilizes the gradient reversing in ARN by replacing the domain classifier with a reconstruction network, and in this manner ARN conducts both feature-level and pixel-level domain alignment without involving extra network structures. Furthermore, ARN demonstrates strong robustness to a wide range of hyper-parameters settings, greatly alleviating the task of model selection. Extensive empirical results validate that our approach outperforms other state-of-the-art domain alignment methods. Moreover, reconstructing adapted features reveals the domain-invariant feature space which conforms with our intuition.